NVIDIA RTX 4000 SFF Ada Generation
GPU
20
GB
PERFORMANCE OVERVIEW
Model
Llama 3.2 1B Instruct
Q4_K - Medium1.5B
Meta Llama 3.1 8B Instruct
Q4_K - Medium8.0B
Qwen2.5 14B Instruct
Q4_K - Medium14.8B
Prompt Speed
8753tokens/s
2004tokens/s
1051tokens/s
Generation Speed
189tokens/s
44.4tokens/s
24.7tokens/s
Time to First Token
179ms
690ms
1.30sec
LocalScore
2100
505
271
COMPARE MODELS
3 models tested
Select Models
Llama 3.2 1B Instruct
Q4_K - Medium
Meta Llama 3.1 8B Instruct
Q4_K - Medium
Qwen2.5 14B Instruct
Q4_K - Medium